Toward Label-Efficient Neural Network Training: Diversity-Based Sampling in Semi-Supervised Active Learning-Reference-Cited by-同舟云学术

Toward Label-Efficient Neural Network Training: Diversity-Based Sampling in Semi-Supervised Active Learning

Published:2023 Issue: Volume:11 Page:5193-5205
ISSN:2169-3536
Container-title:IEEE Access
language:
Short-container-title:IEEE Access

Author:

Buchert Felix¹,Navab Nassir¹^ORCID,Kim Seong Tae²^ORCID

Affiliation:

1. Chair for Computer Aided Medical Procedures, Technical University of Munich, München, Germany

2. Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, South Korea

Funder

Kyung Hee University in 2021

National Research Foundation of Korea (NRF) Grant through the Korea Government

Institute of Information and Communications Technology Planning and Evaluation (IITP) Grant through the Korea Government (MSIT), Artificial Intelligence Innovation Hub

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

General Engineering,General Materials Science,General Computer Science,Electrical and Electronic Engineering

Link

http://xplorestaging.ieee.org/ielx7/6287639/10005208/10015727.pdf?arnumber=10015727

Reference46 articles.

1. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results;tarvainen;Proc Conf Neural Inf Process Syst (NIPS),2017

2. Combining MixMatch and active learning for better accuracy with fewer labels;song;arXiv 1912 00594,2019

3. Active learning for convolutional neural networks: A core-set approach;sener;Proc Int Conf Learn Represent (ICLR),2018

4. Active Hidden Markov Models for Information Extraction

5. Regularization with stochastic transformations and perturbations for deep semi-supervised learning;sajjadi;Proc Conf Neural Inf Process Syst (NIPS),2016

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. An Active Regression Learning Method for Quality Evaluation of Molecular Dynamics Data;2024 4th International Conference on Electronic Materials and Information Engineering (EMIE);2024-06-12

2. Expanding the Applicability Domain of Machine Learning Model for Advancements in Electrochemical Material Discovery;ChemElectroChem;2024-02-09

3. Overcoming Overconfidence for Active Learning;IEEE Access;2024